The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

KNN: Multiclass Classification

library(mlexperiments)

See https://github.com/kapsner/mlexperiments/blob/main/R/learner_knn.R for implementation details.

Preprocessing

Import and Prepare Data

library(mlbench)
data("DNA")
dataset <- DNA |>
  data.table::as.data.table() |>
  na.omit()

feature_cols <- colnames(dataset)[1:180]
target_col <- "Class"

General Configurations

seed <- 123
if (isTRUE(as.logical(Sys.getenv("_R_CHECK_LIMIT_CORES_")))) {
  # on cran
  ncores <- 2L
} else {
  ncores <- ifelse(
    test = parallel::detectCores() > 4,
    yes = 4L,
    no = ifelse(
      test = parallel::detectCores() < 2L,
      yes = 1L,
      no = parallel::detectCores()
    )
  )
}
options("mlexperiments.bayesian.max_init" = 10L)

Generate Training- and Test Data

data_split <- splitTools::partition(
  y = dataset[, get(target_col)],
  p = c(train = 0.7, test = 0.3),
  type = "stratified",
  seed = seed
)

train_x <- model.matrix(
  ~ -1 + .,
  dataset[data_split$train, .SD, .SDcols = feature_cols]
)
train_y <- dataset[data_split$train, get(target_col)]


test_x <- model.matrix(
  ~ -1 + .,
  dataset[data_split$test, .SD, .SDcols = feature_cols]
)
test_y <- dataset[data_split$test, get(target_col)]

Generate Training Data Folds

fold_list <- splitTools::create_folds(
  y = train_y,
  k = 3,
  type = "stratified",
  seed = seed
)

Experiments

Prepare Experiments

# required learner arguments, not optimized
learner_args <- list(
  l = 2,
  test = parse(text = "fold_test$x"),
  use.all = FALSE
)

# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
predict_args <- list(type = "response")
performance_metric <- metric("bacc")
performance_metric_args <- NULL
return_models <- FALSE

# required for grid search and initialization of bayesian optimization
parameter_grid <- expand.grid(
  k = seq(4, 68, 6)
)
# reduce to a maximum of 10 rows
if (nrow(parameter_grid) > 10) {
  set.seed(123)
  sample_rows <- sample(seq_len(nrow(parameter_grid)), 10, FALSE)
  parameter_grid <- kdry::mlh_subset(parameter_grid, sample_rows)
}

# required for bayesian optimization
parameter_bounds <- list(k = c(2L, 80L))
optim_args <- list(
  iters.n = ncores,
  kappa = 3.5,
  acq = "ucb"
)

Hyperparameter Tuning

Bayesian Optimization

tuner <- mlexperiments::MLTuneParameters$new(
  learner = LearnerKnn$new(),
  strategy = "bayesian",
  ncores = ncores,
  seed = seed
)

tuner$parameter_grid <- parameter_grid
tuner$parameter_bounds <- parameter_bounds

tuner$learner_args <- learner_args
tuner$optim_args <- optim_args

tuner$split_type <- "stratified"

tuner$set_data(
  x = train_x,
  y = train_y
)

tuner_results_bayesian <- tuner$execute(k = 3)
#> 
#> Registering parallel backend using 4 cores.

head(tuner_results_bayesian)
#>    Epoch setting_id  k gpUtility acqOptimum inBounds Elapsed      Score metric_optim_mean errorMessage l use.all
#> 1:     0          1 16        NA      FALSE     TRUE   1.061 -0.1651140         0.1651140           NA 2   FALSE
#> 2:     0          2 64        NA      FALSE     TRUE   1.131 -0.1261065         0.1261065           NA 2   FALSE
#> 3:     0          3 10        NA      FALSE     TRUE   1.060 -0.1835086         0.1835086           NA 2   FALSE
#> 4:     0          4 34        NA      FALSE     TRUE   1.074 -0.1377516         0.1377516           NA 2   FALSE
#> 5:     0          5 58        NA      FALSE     TRUE   1.101 -0.1247624         0.1247624           NA 2   FALSE
#> 6:     0          6 28        NA      FALSE     TRUE   1.046 -0.1462823         0.1462823           NA 2   FALSE

k-Fold Cross Validation

validator <- mlexperiments::MLCrossValidation$new(
  learner = LearnerKnn$new(),
  fold_list = fold_list,
  ncores = ncores,
  seed = seed
)

validator$learner_args <- tuner$results$best.setting[-1]

validator$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models

validator$set_data(
  x = train_x,
  y = train_y
)

validator_results <- validator$execute()
#> 
#> CV fold: Fold1
#> 
#> CV fold: Fold2
#> CV progress [======================================================================>-----------------------------------] 2/3 ( 67%)
#> 
#> CV fold: Fold3
#> CV progress [==========================================================================================================] 3/3 (100%)

head(validator_results)
#>     fold performance  k l use.all
#> 1: Fold1   0.8931022 58 2   FALSE
#> 2: Fold2   0.8445084 58 2   FALSE
#> 3: Fold3   0.9010913 58 2   FALSE

Nested Cross Validation

Inner Bayesian Optimization

validator <- mlexperiments::MLNestedCV$new(
  learner = LearnerKnn$new(),
  strategy = "bayesian",
  fold_list = fold_list,
  k_tuning = 3L,
  ncores = ncores,
  seed = seed
)

validator$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"


validator$parameter_bounds <- parameter_bounds
validator$optim_args <- optim_args

validator$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models

validator$set_data(
  x = train_x,
  y = train_y
)

validator_results <- validator$execute()
#> 
#> CV fold: Fold1
#> 
#> Registering parallel backend using 4 cores.
#> 
#> CV fold: Fold2
#> CV progress [======================================================================>-----------------------------------] 2/3 ( 67%)
#> 
#> Registering parallel backend using 4 cores.
#> 
#> CV fold: Fold3
#> CV progress [==========================================================================================================] 3/3 (100%)
#> Registering parallel backend using 4 cores.

head(validator_results)
#>     fold performance  k l use.all
#> 1: Fold1   0.8702444 28 2   FALSE
#> 2: Fold2   0.8396360 64 2   FALSE
#> 3: Fold3   0.9010913 58 2   FALSE

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.